Revision History
MedQA · 8 revisions
Sizes are character counts of the article source. The signed number is the change from the previous revision.
Recent edit summaries
Detailed summaries recorded by editors. Generic maintenance summaries are omitted here; every recorded revision remains below. Dates describe the edit, not necessarily the event it covers.
- Update: regenerate results chart from the fact-checked results table
Version 8 · Nov 5, 2026, 05:40 AM
- Correction: Corrected GPT-4's MedQA score (81.4% for the released model; 86.1% was the non-production GPT-4-base), fixed the 50.8% and 60.2% GPT-3.5 results that were misattributed to a ChatGPT USMLE study, removed a fabricated phrase and an unsupported question-source breakdown attributed to the original paper, corrected the Taiwan subset's textbook corpus, and updated the leaderboard and saturation status after Vals.ai archived MedQA in April 2026 (plus 15 minor fixes)
Version 7 · Nov 5, 2026, 05:39 AM
- Improve internal links (2026-10-13)
Version 5 · Oct 13, 2026, 10:14 AM
- Added 6 contextual internal links
Version 4 · Jul 23, 2026, 03:27 PM